ES2807724T3 - Improved method and relevant apparatus for determining body condition score, body weight and fertility status - Google Patents

Abstract

Method for determining a numerical index indicative of the energy reserves in the form of fat stored by a dead or live animal (107) of any species and race, including humans, for example, the body condition score or the body mass index, in which the following stages are carried out: A. digital detection, by means of optical detection of reference elements, applied or projected on the body of the observed subject, or by another type of detection system, with contact or without contact, of at least one profile (109) of an anatomical region of morphological interest, said at least one profile being defined as the shape of the curve that describes at least part of the outer perimeter of a section of said anatomical region, crossing said curve that extends over an imaginary plane said anatomical region; B. sending said at least one profile (109) from step A to at least one data processing unit (E); C. calculate a numerical index R indicative of the energy reserves in the form of fat accumulated by the animal, in particular, in said anatomical region, by means of at least one data processing unit (E) on the basis of said at least one profile (109) of stage A; and D. correlating, in said at least one data processing unit (E), by means of a predefined mathematical transformation, said numerical index R with one or more state characteristics of said animal; wherein in the body of the animal a first side (LS or RS) of said anatomical region is present with respect to the spine of the animal (S) or a first side and a second side (LS, RS) of said anatomical region with respect to the vertebral column (S) of the animal, and in which said profile includes a point of relative maximum PM in the vertebral column of the animal and a first development of the profile (109L or 109R) on said first side or a first and a second development of the profile (109L and 109R) respectively on said first and second side (LS, RS), the method being characterized in that stage C includes the following sub-stages: C1. individualize the coordinates of the relative maximum point PM of said profile; C2. determine a first straight line (β) tangent to said profile (109), starting said first straight line from the relative maximum point PM and touching said profile at a first point of tangency P1 of said first side, or in addition to the first straight line of tangency that also determines a second straight line of tangency (α) that extends from the point of relative maximum PM and touches said profile at a second point of tangency P1 'on said second side; C3. in the case in which in stage 2 only said first point of tangency P1 was calculated, taking as the second development (109L, 109R) of said profile the specular projection of said first development with respect to the direction of the spine, and assuming as the second point of tangency P'1 the specular point to said first point of tangency P1 with respect to the direction of the spinal column; C4. calculating a first dotted line point P2 and a second dotted line point P'2 as the intersection between said profile and a straight line (γ) parallel to a base segment running from P1 to P'1; C5. calculate said numerical index R as: R = ∫ (α1, α2, α'1, α'2) in which α2 is the angle between the segments PMP2 and P2P'2, α1 is the angle between the segments P2P1, and P1P '1, α'2 is the angle between the segments PMP'2 and P'2P2, α'1 the angle between the segments P'2P'1 and P'1P1, and in which α2 = α'2 and α1 = α'1 in case of the assumption of step C3.

Description

DESCRIPTION

Improved method and relevant apparatus for determining body condition score, body weight and fertility status

The present invention relates to a method for determining the body condition score (BCS), body weight and fertility status of a living being.

Furthermore, the present invention also relates to apparatus for the evaluation of the body condition, the body weight and the fertility status of a living being, which implement the method.

More precisely, the present invention relates to a method for calculating the body condition score or BCS by processing the profile of one or more anatomical regions of the observed subject, which makes use of at least one profilometer, at least one data processing unit and at least one program implementing specific processing of the profile. Said profile is defined herein as the shape of the curve that describes at least part of the external perimeter of a section of an anatomical region of the subject under examination, this curve being arranged on an imaginary plane that crosses said anatomical region. In particular, the method according to the present invention requires a profile whose size and shape are linked by any relation of proportionality (also unknown) with the absolute size and physical shape of the subject.

This method introduces a new dimensionless indicator of body condition, called the synthetic fattening index or the FI or R fattening index, which, unlike the body condition score, is invariable with respect to species, breed, sex, the age and absolute size of the observed subject.

This method also makes it possible to determine, to a good approximation, the body weight of a living being on the basis of the synthetic fattening index FI (or equivalent body condition) and other information characteristics of the subject, such as species, breed, sex, age.

This method also introduces a new indicator of the fertility status of the observed subject. This index is the combination of the FI fattening index (or equivalent body condition score) with the heat status. The sole indication of heat is commonly used today to maximize the chances of success in artificial insemination. However, a subject may be in heat, but not in a suitable body condition for conception. The fertility index presented and implemented here has the purpose of improving the heat indicator, enriching it with the information of the body condition, obtaining the fertility index F.

The method introduced here for the measurement of body condition, weight and fertility index also turns out to be robust to possible errors in the use of the devices by an operator and possible variations of the skeleton between different subjects.

Said method also has the advantage over the known prior art of being able to be implemented even in simple devices (eg smart phones) without the need for additional apparatus. This is a direct consequence of the fact that in the method of the invention the profile is analyzed, leaving aside its absolute physical size.

State of the art

Every living being, to perform its biological functions, needs energy that is always available. As regards the animal kingdom, to which the invention is directed, energy is extracted from food and stored in the body in the form of fat reserves.

The body condition score or BCS is a method of evaluating an animal's body condition, or its energy reserves, which is traditionally carried out in a visual and / or tactile manner by a properly trained technician.

Normally, in the case of body condition assessment in cattle, this score is determined on the basis of a scale of 1 to 5 (other different scales are used in different countries, however, they are related to each other by transformations linear), in which the minimum score of 1 corresponds to a very thin subject and the maximum score of 5 corresponds to an obese subject.

Intermediate scores indicate: 2 thin person, 3 fit person, 4 fat person.

The above scale also provides intermediate quarter point scores, such as 2.25 or 3.75 scores, and the like.

In the following, BCS measured on a scale of 1 to 5 will be considered, although, throughout the world, BCS scales are used with scores ranging from 0 to 5 (in France), from 1 to 9 (or similar), which in any case they are mutually linked to each other by a linear transformation.

Since BCS is a subjective visual assessment and depending on the breed and species, differences were observed. Considerable among the surveys carried out by different technicians (problems of subjectivity and repeatability of the evaluation). This results in significant errors in the application of the predictive models described in the prior art, which are based on BCS for the evaluation of animal health, for the balance of the food ration in specific phases of the animal's life, for the diagnosis of metabolic diseases, for assisted fertilization, etc.

In intensive farming of production animals (e.g. cattle, sheep and goats, pigs), BCS is a useful analysis tool for the health status and energy balance of animals, capable of providing, by means of proper processing, general guidelines on feed rations used and on reproductive management.

In the framework of herds for milk production, it was shown that the evaluation of body weight alone is not a good indicator of the process of mobilization of fat for milk production. For this reason, the body condition score assessment method has received considerable consideration as a means of estimating tissue mobilization, for example, in the dairy cattle field (Domecq et al., 1997b; Flamenbaum et al., 1995 ).

For ease of discussion, in the following description, the specific field of intensive cattle milking will primarily be considered, without limiting the applicability of the invention to any other species in the animal kingdom. Each consideration herein is readily translatable in the context of any other higher animal species.

In dairy cows, obesity can be the result of inadequate feeding in the last 3-4 months of lactation, a period in which milk production begins to fall naturally and meat tends to to accumulate in stores of excess in the body.

Even excessively long periods outside of lactation ("dry" period) or rich nutrition also at this stage can lead to excessive body condition of the animal (overcondition).

It is known that a bovine that is too fat is more likely to be subject to difficult calvings and, after calving, will undoubtedly present a very poor dry matter intake, with an increased incidence of metabolic problems, such as fat cow syndrome, ketosis, and the like, and consequently production drops. Excessive leanness (subcondition) instead can cause low milk production and low fat content in milk, due to insufficient energy and protein stores.

It is known that cows are also called calves, heifers or cows on the basis of age; In particular, calves are beef from zero to one year of age, heifers from one to three years of age, and cows for three years or less than three years if they have calved at least once.

BCS can be used usefully for the management of heifers to assess, in lean subjects, the possibility that they do not grow fast enough to allow the achievement of puberty at around 13-15 months of age, with problems of inadequate size in a first parturition and the consequent low production during the later lactation.

On the other hand, it is shown that heifers that are too fat have lower productions compared to other beef with adequate weight at maturity.

The body condition of the cow is in continuous change during the lactation cycle and consequently also the ideal BCS varies depending on the lactation stage, according to known patterns, such as, for example, the one shown in the Figure 1 attached.

Young cows are in the condition of negative energy balance and mobilize body reserves to cope with this phase, in which, for every pound of weight mobilized, milk production increases by approximately seven pounds.

Cows or beef in late lactation are in positive balance and tend to regain lost body condition immediately after calving.

In general, the BCS assessment can provide valuable information on the health of observed animals, whether for production (ie, cattle, goats, pigs, and horses) or for companionship (eg, dogs and cats).

As shown in Figure 3 attached in this document, the traditional method of evaluation is based on the visual and tactile appreciation of BCS of pre-established areas of the body, identifiable mainly at the level of the buttocks, lower back, posterior part, haunches. , tip of the buttock and base of the tail, possibly in relaxed subject conditions, because muscle stiffness can compromise the accuracy of the observation.

It is well known that this type of visual and tactile evaluation of the BCS has great disadvantages, such as the high Subjectivity of the evaluation, which implies a poor repeatability of the numerical value, over time, for the same technician and for different technicians, the significant amount of time required to carry out the necessary observations on the animal and the high cost associated with continuous training of technicians. Recently, this method of visual and tactile evaluation has been simplified through the use of computer media, such as application programs for personal notebook computers, PDAs, smart phones and tablets.

These application programs guide the evaluator in the recognition of morphological features that are associated with a given score, to reduce the time required to measure, transcribe, transmit and process the BCS. There are also more recent programs, in which one tries to reduce the number of morphological characters to observe, as well as to further reduce the time required. In any case, it is the evaluator who, although guided, expresses the judgment. Therefore, there is still the problem of subjectivity in measurement and its poor repeatability.

There are also programs that allow capturing photos of animals from different points of view and offer graphic tools to highlight in the image, in post-processing, the main morphological features. However, the images do not appear as long as they are of good quality, since an image exposed in an inappropriate way can be too dark or too light, erasing the shadows that provide information about the three-dimensionality of the surface of the body of the observed subject. However, it is the technician who performs the work of recognition of the morphological features, so that the subjective nature of the measurement remains.

Subsequently, automated systems have been developed for BCS and weight assessment using two-dimensional image analysis.

An example is represented by document US5474085, in which a static type system is described, which performs a thermographic evaluation of animals. In this case, considering the static nature of the geometric model, the number of pixels in the thermal image associated with an animal is directly correlated with its weight.

A further example is represented by documents US5483441 and US5576949, which describe systems that analyze a plurality of two-dimensional images, such as simultaneous images from above and from the side of the animal and / or images made at successive times in a moving animal. , within a system of cameras and sensors with fixed and known geometry.

These types of systems allow the determination of absolute measurements, such as height, width and length, from which BCS and / or weight can be derived by comparison with animal models with known characteristics.

Another example is represented by document US5944598, which describes a system that extracts the profile of the animal from an image and determines the geometric parameters of the system, by evaluating the distance between the observed object and the measurement tool, for example, a laser rangefinder. From the profile, morphological and / or massive evaluations are derived.

The main limitation of these automated evaluation systems is the complexity of the general application of the solution in the framework of a barn. This implies a high cost, little robustness of the solution and little precision and repeatability of the results.

Recently, automatic systems have been developed for the evaluation of BCS and weight by means of three-dimensional scanning.

An example is represented by document US20140029808, which describes a system that performs a three-dimensional scan, for example, by means of time-of-flight (TOF) laser rangefinders, which estimate the BCS by analyzing a cloud of points, comparing them with a set of reference standards associated with different values of the BCS.

Another example is represented by document US8351656, which describes a system that performs a scan in three dimensions, for example, by means of structured light, stereoscopic cameras and laser rangefinders, which estimate the weight by analyzing the points of the generated cloud. by the acquisition systems and comparing them with a set of reference models.

In this case, the device is made as a portable solution and a series of mathematical solutions are applied to determine the orientation and location of the animal with respect to the measurement tool.

Another document, US6377353, makes use of the method described above to derive morphometric evaluations. Document US6549289 describes the same principle of three-dimensional analysis using structured light, observed by a stereoscopic camera system, applied by performing triangulation calculations.

Even in the case of this class of solutions, the main limitation consists in the high complexity of the technological solution that is poorly adjusted to the field of application of the barn and the training of the technicians who normally operate in it.

These solutions are therefore very expensive, very delicate and therefore unreliable in field application.

Furthermore, these solutions show poor precision and repeatability of the results.

There are even patents like EP1537531 B1 (from WO 2004/012146 A1) and EP2370952B1 also characterized by the detection of the point cloud of an anatomical region by three-dimensional scanning. These patents implement different methods of examining the main curvatures of the observed surfaces, which however fully exploit the characteristics of the three-dimensional scan, which allows to detect the absolute coordinates of the detected points and then the absolute size.

These methods therefore require a three-dimensional scanning system and are therefore not applicable in simple devices, such as those equipped with a single two-dimensional camera (eg smart phones).

Furthermore, products based on these methods have been shown to be inaccurate and repeatable across body condition measurement scale limits (eg BCS <2 for a very lean subject and BCS> 4 for a very fatty subject), exactly where the diagnosis is more useful to define the most appropriate intervention to restore an adequate type of body condition.

Other similar solutions are given in:

- US 2005/257748 A1, LEROY T ET AL: "Automatic determination of body condition score of dairy cows based on 2D images", EUROPEAN LIVESTOCK PRECISION CONFERENCE 2, 2005, UPPSALA, WAGENINGEN ACADEMIC PUBL, NL, 1 January 2005, pages 251-255, XPO09127881, ISBN: 978-90-76998-68-8,

- WO 2010/063527 A1 (DELAVAL HOLDING AB [SE]; LIAO BOHAO [SE]; KRUKOWSKI MARILYN [SE]) June 10, 2010,

- EP 2027770 A2 (ICEROBOTICS LTD [GB]) February 25, 2009,

- Marilyn Krukowski: "Automatic determination of the body condition score of dairy cows from 3D images", Master's thesis in computer science, ISSN: 1653-5715, January 26, 2009 (01-26-2009) , pages 1-89, XP055051333, D6 KTH, Stockholm, Sweden, http://www.csc.kth.se Retrieved from the Internet: URL: http://www.nada.kth.se/utbildninglgrukthlexjobblrapportlistor/2009/ rapporter09 / kruk0wski marilyn 09009.pdf [retrieved on 01/28/2013];

- US 2013/201470 A1 (ALLISON DAVID [US] ET AL) October 3, 2013;

- WO2010 / 107383 in (INNOVATOR SKAANE AB [SE]; FLODMARK CARL-ERIK [SE]) September 23, 2010; and WO96 / 04551 A1 (MEAT RESEARCH CORP [AU]; FORREST ALEXANDER [AU]; GORDON ANTHONY JOHN [) February 15, 1996.

In view of the above, therefore, it is an object of the present invention to provide a method and an apparatus which overcomes the disadvantages of the prior art.

In particular, an object of the present invention is to implement a method for calculating the relevant FI and BCS, body weight and fertility status, which is automatic and easy to implement.

Another object of the present invention is to provide apparatus for applying the method, which are cheap, easy to manufacture, robust and compatible with the environment of use and applicable to any animal, regardless of the species, breed, gender, age and absolute size. .

Therefore, the object of the present invention is a method and apparatus as defined by the independent claims.

Some preferred embodiments are defined in the dependent claims.

Description of the invention

The present invention will now be described, for illustrative but not limiting purposes, according to its preferred embodiments, with particular reference to the figures of the attached drawings, in which:

- Figure 1 shows a graph of the prior art that represents the typical trend of the value of the score of the body condition (dashed line) and the milk production (solid line) of a bovine in good health as a function of the days of lactation (reported on the abscissa);

- Figure 2 highlights some examples of the anatomical region of morphological interest, such as the lumbar (L), abdominal (A), sacral (S), femoral (F), pectoral (P), gluteal (G) and dorsal regions. (D) in different species of animals and in man;

- Figure 3 shows a relevant prior art graph for the correspondence between an animal's body condition and the relevant BCS score;

- Figure 4 shows the prior art graphs relating to the correspondence between the body condition of a human being and the corresponding BMI score;

- Figure 5 shows a block diagram of the apparatus of the present invention;

- Figure 6a shows a first embodiment of the apparatus of Figure 5, of the portable type with manual control, which implements a profilometer of the optical type;

- Figure 6b shows the apparatus of Figure 6a in use by a technician in the field of a dairy herd;

- Figure 7 shows the lumbar profile in a dairy cow, in a top view;

- Figure 8 shows a procedure of said profile of Figure 7;

- Figure 9 shows the step of determining the points of tangency to the profile according to the method of the present invention;

- Figure 10 shows a block diagram of the method for determining the points of tangency to the profile; - Figure 11 shows a second embodiment of the apparatus of Figure 5, of a fixed automatic type applied in a weighing box;

- Figure 12 shows the same second embodiment of the apparatus of Figure 5, of the fixed automatic type applied in a rotary type milking parlor;

- Figure 13 shows a third embodiment of the apparatus of Figure 5, of the automatic type, mobile on an aerial guide in an angular milking parlor;

- Figure 14 shows a block diagram related to the acquisition and control functions in the first embodiment of the apparatus of the invention;

- Figure 15 shows a block diagram related to the acquisition and control functions in the second and third embodiments of the apparatus of the invention;

- Figure 16 shows a block diagram related to the preprocessing and processing functions present in all the embodiments of the apparatus of the invention;

- Figure 17 shows a fourth embodiment of the apparatus of Figure 5, of the static automatic type of gap, the gap being able to cross the gap freely by animals;

- Figure 18 shows a first example of highlighting the profile by means of colored paint applied manually; - Figure 19 shows a second example of highlighting the profile by means of colored paint applied automatically;

- Figure 20 shows a third example of highlighting the profile by applying a colored adhesive; - Figure 21 shows a further embodiment of the apparatus of Figure 5, of the static automatic type, obtained by placing a suitable number of high resolution cameras on the animal housing box;

- Figure 22 shows a further embodiment of the apparatus of Figure 5, of the static manual type, in which the profile is acquired by means of a specific comb profilometer of the electronic type;

- Figure 23 shows a further embodiment of the apparatus of Figure 5, of the automatic dynamic type, in which the profile is acquired by means of an adhesive strip equipped with a set of flexible sensors of electronic type; Y

- Figure 24 shows a further embodiment of the apparatus of Figure 5, in which the profile is acquired by means of of a three-dimensional scanner, for example, of the type of time of flight (TOF).

The object of the present invention is an apparatus and a method for calculating a new synthetic fattening index FI by detecting and processing some morphological traits in animals. From the latter the body condition score or BCS is derived. The combination of said FI and other characteristic parameters of the morphology and behavior of the observed subject, body weight and a synthetic evaluation index of the fertility status are calculated.

With reference to Figure 5, an apparatus D for the method according to the present invention is shown, in which said method consists of detecting a profile of one or more anatomical regions of the observed subject, using at least one profilometer, of at least one data processing unit and at least one program that implements a specific processing method. Said profile is defined herein as the shape of the curve that describes at least part of the outer perimeter of a section of an anatomical region of the subject under examination, this curve being arranged in an imaginary plane that crosses said anatomical region. In particular, the method according to the present invention requires a profile whose size and shape are linked by any relation of proportionality (also unknown) with the size and absolute physical shape of the subject.

Said profile is then processed by a data processing unit, in order to obtain a numerical synthetic index that represents the fat reserves, and then the body condition of the subject itself. The apparatus D comprises at least one profilometer (which in the case of the figure is constituted by a camera 102), at least one control unit 101 and at least one data processing unit E. In the case in which the unit data processing is remote, the apparatus D will include at least one data communication unit.

There are a number of physical principles used to detect, with or without contact, such a profile in a curved surface space. Among them, there is someone who is particularly suited to the field under examination. By way of example, but not limitation, some particular applications of these principles will be illustrated in accordance with the purposes of the present invention. These applications can be divided into two main categories: (a) non-contact profile detection, (b) contact profile detection.

In general, it is worth considering that, according to the purposes of the present invention, the method used must be compatible with the application in the open field, in the case of animals that live with a more or less irregular coat, depending on the species and the race.

Among the non-contact applications between the instrument and the body of the subject under consideration are included solutions based on the analysis of images detected by a two-dimensional camera. In this case, in order to highlight a specific anatomical region of the observed subject, so that it can be detected by means of a video recording apparatus, a structured light source can be used. Assuming that the pattern consists of one or more rows transverse to the subject's spine observed in a specific anatomical region (e.g. lumbar (L), abdominal (A), sacrum (S), femoral (F), pectoral ( P), gluteal (G), dorsal (D) or skull in some special cases), it is possible to project a pattern (structured light) on the body of the subject under examination, in the anatomical region of interest. In this case, apparatus D will include a coherent (for example, a laser line generator) or non-coherent light source 103, this light source projecting a set of discrete or continuous points onto the subject, to highlight a profile 109 of the morphological region of interest

This method uses the principle of optical triangulation, a technique that allows the calculation of the distances between the points by exploiting the properties of the triangles. This principle requires the exact knowledge of the relative position of the camera in relation to the structured light source and the observed object, as this is essential to calculate the absolute coordinates in space of the detected objects.

In the method according to the present invention there is no need to know the absolute size of the observed object, therefore the principle of optical triangulation can be applied regardless of the relative position of the camera with respect to the structured light source and to the observed object.

Such a feature allows the anatomical region of interest to be highlighted, even with other techniques, such as:

a) drawing a pattern on the body of the subject or animal, in the anatomical region of interest, for example, by painting with a colorful paint a set of discrete or continuous points (for example, line transverse to the spine);

b) highlighting the anatomical region of interest by applying an adhesive film, which represents the pattern to be used for the next stage of analysis;

c) highlighting the anatomical region of interest by applying an elastic band, which represents the pattern to be used for the next stage of analysis, around the anatomical region of interest.

In this case, the principle of optical triangulation is also used, but, in the absence of information about the geometry of the measurement system, it is possible to detect only the proportionality information and not to obtain absolute measurements. For the method according to the present invention, the proportionality information is sufficient, even if the detections containing absolute measurements can be exploited.

Preferably, the pattern used corresponds to a line in high contrast with respect to the color of the surface of the observed subject, placed transversely to the spine in the median area of the specific anatomical region under examination (for example, the loins, mid path between the bumps of the hips and the beginning of the chest, as shown in the case of cattle in Figures 2a, 6b and 7).

Within the framework of non-contact detection solutions for such contour lines 109, the apparatus D comprises a camera 102, adapted to acquire at least one two-dimensional image of said profile, highlighted with one of the methods described.

Alternatively, the camera can be a three-dimensional type (3D scanner), for example, of the time of flight (TOF) type or of the stereoscopic type, in combination with a control unit that extracts the profile 109 from the point cloud of three-dimensional scanning. In this case, it is sufficient to focus on the anatomical region of interest, without highlighting the profile with one of the methods described.

The fact is emphasized that the present method is independent of the detection of absolute measurements, therefore, it can be applied indifferently on conventional cameras (2D) and three-dimensional cameras (3D), for example, stereoscopic type, time of flight, or phase shift. For this same reason, the relative position of the recording device with respect to a possible laser generator is not relevant.

Among the applications with physical contact, are those based on contact profilometers, such as the needle profilometer or gauge comb. This tool makes it possible to detect the profile of a surface along a plane that crosses said surface and is made up of a set of parallel, coplanar and aligned needles, mobile along one direction. This tool allows the profile 109 to be detected mechanically. The position of the individual needles is measured and digitized to reconstruct a computerized image of the profile 109.

Even among applications with physical contact are those that consist of detecting the contour 109 by means of flexural sensors. This system consists of a sequence of sensors positioned continuously along a band. Each sensor indicates its degree of bending to a control unit that determines the relative position of all sensors along the strip, reconstructing a computerized image of the profile 109.

All the possible implementations described herein output an image of the profile 109 that the control unit 101 preprocesses and sends to the data processing unit E. The apparatus implementing the method according to the present invention may comprise also P-position sensors, including the tilt sensor, such as accelerometers, gyroscopes, and magnetometers.

Such apparatus can also include spatial location systems (eg, global positioning system or GPS).

Said apparatus may further comprise a radio frequency reader (for example, RFID ISO11784-785) that facilitates the electronic identification of the animals.

Said apparatus can also comprise a system for the identification and real-time spatial location of the observed subjects (real-time location system or RTLS) that allows the detection of their position and instantaneous behavior.

Said apparatus may further comprise a system for detecting the state of heat of the observed subject. In the case of dairy cattle, pedometers are used (for the detection of the sudden increase in mobility in relation to the appearance of heat), or video systems to detect the mounting reflex by means of the glue painting technique, or systems of detection of heat by chemical analysis of milk or blood (for example, detection of progesterone concentration). The combination of the heat status with the BCS evaluation allows defining a new index, the fertility index defined here, as described below.

Said apparatus can interact with a local unit control 101, which provides data pre-processing, such as data encryption and compression, in-image storage, for example, by means of watermarking techniques. , accessible via a user interface, possibly provided with an extension arm 105 to simplify proper targeting of the anatomical region of interest.

This data is then transmitted to a data processing unit E which provides its processing by means of an algorithm which will be described in detail below. The data processing unit is preferably considered remote. This solution provides more computing power, smoother code corrective and evolutionary maintenance, and business continuity and disaster recovery (BC / DR) policy compliance for data protection.

Although, however, it does not exclude the possibility that the processing unit E can be integrated within the control unit 101.

Said apparatus D can be constituted by at least one smartphone equipped with an appropriate software application to perform detection, a first data processing, direct processing or the transmission and reception of data and display of results.

In general, the method provides for processing in at least one E unit processing data of at least one profile as defined above by a processing method, to obtain a numerical index R indicative of the amount of energy reserves in the form of fat accumulated by the animal, in particular, in said anatomical region.

The method also provides correlation by means of said at least one data processing unit, by means of a predefined mathematical transform, said numerical index R with one or more state characteristics of said animal. The numerical parameters of said mathematical transform can depend at least by species and breed of the animal and are obtained in comparison with a reference population evaluated visually according to a traditional method or a different reference method.

Referring to Figures 6a and 6b, a first embodiment of apparatus D comprises an extension arm 105 which is grasped by a technician 108 at a first end and which supports the control unit 101 at a second end. Button 106 allows the technician to control the shutter of a photograph even when the apparatus is fully stretched in the measurement position, as illustrated in Figure 6b.

Said control unit 101 can in this case be a smartphone, in which the camera 102 is integrated. At the second end of the extension arm 105, a laser arm can optionally be connected, thus forming a suitable angle between them that makes it easier for the technician 108 to place the laser 103 in the lumbar region 109 of the animal. observed. In a preferred, but not limiting way, this angle is 135 °. This solution is particularly advantageous in the dairy cattle field, which is characterized by a significant size compared to the operator 108.

At the end of the laser arm, the laser generator 103 is connected, which is controlled by the control system 101, which in turn receives the release command from the technician 108 by means of the button 106 placed in correspondence with the first end of said extension arm 105.

Even the user interface built into the control unit 101 provides redundant and feedback control commands with respect to the button 106. Typically, the button 106 is useful in the event that the BCS is measured for subjects that are large compared to the size of the technician 108, such as in the case of a bovine animal 107.

In the case of small objects, such as sheep and goats, the technician 108 can hold the arm 105 in the vicinity of the control unit 101, thus being able to interact directly with the user interface.

After the technician 108 has shown the region of the body under observation by one of the methods described above (when necessary), the apparatus D will be positioned to shoot with the camera 102 that region.

Technician 108 presses actuator 106 to adjust profile 109 via camera 102.

The purpose of such apparatus D is to detect at least one profile 109 of at least one morphological anatomical region of interest (e.g. lumbar (L), abdominal (A), sacral (S), femoral (F), initial number (P) ), gluteal (G), dorsal (D)) of subject 107. Other regions may also be of interest, although for special cases (eg, wild animals).

Said profile is defined herein as the shape of the curve that describes at least part of the outer perimeter of a section of an anatomical region of the subject under examination, this curve being arranged in an imaginary plane that crosses said anatomical region. In particular, the method according to the present invention requires a profile whose size and shape are linked by any relation of proportionality (also unknown) with the size and absolute physical shape of the subject.

The control unit 101, using known techniques, encrypts and compresses in a single package the image, the personal data of the observed subject and, if available, the data recorded from the following sensors: a) position sensors P, such as a san accelerometer and / or a magnetometer and / or a gyroscope and / or a GPS and / or a Wi-Fi locator;

b) RFID identification systems and the like;

c) RTLS real-time identification and location systems and the like;

d) heat detection or heat detection systems and the like.

The control unit 101 then provides the transmission of said encrypted and compressed data packet to the data processing unit E.

Said data processing unit E provides the decryption, using known techniques, of the information received, registering them in a database and associating them with the records of the subject under consideration 107.

The data processing unit E will extract and process the image, automatically or semi-automatically, with the appropriate prior art procedures for digital processing, to efficiently and effectively extract the coordinates of the pixels that describe the profile 109 in the domain from image.

The coordinates of these pixels can then be used to determine, according to the method to be described below, the points of maximum P ^m , tangency P1 and P1 and intermediate points P2 and P2, which are shown in Figures 7 and 8.

Using the mathematical formula that will be indicated below, the processing unit E can calculate the value of a synthetic index of fattening FI, from which the BCS will be derived, associate it with the measurement date and store it in a database in the registry of the subject under examination 107, duly identified by a unique identification number.

With reference to Figures 9 and 10, the method for determining the FI subject of the invention is applicable regardless of the species, race, gender, age and absolute size of the observed subject 107.

The method is also robust to possible errors in the use of the devices by an operator and / or to skeletal variations between different subjects.

The synthetic fattening index evaluation method, corresponding to the body condition of the observed subject, is based on the evaluation of fat present in at least one anatomical morphological region of interest (for example, lumbar (L), abdominal (A), sacrum (S), femoral (F), pectoral (P), gluteal (G), dorsal (D)) of subject 107. A calculation method is proposed, which takes into account a profile 109 of an anatomical region of the subject 107 Such a profile can be obtained with an optical triangulation profilometer using a two-dimensional camera in combination with one of the following methods to highlight the anatomical region of the observed subject. The first method is to use a colored paint to draw a suitable pattern in the selected anatomical region. Such paint can be applied, for example, by hand with a brush or a crayon, to obtain a line transverse to the spine. Similarly, a pre-cut adhesive template can be used, which is applicable to said anatomical region, onto which the colored paint will be sprayed with a spraying tool (see Figure 18). An additional possibility is to automate the application by means of a tool provided with a suitable number of nozzles to spray the paint according to the pattern defined manually or automatically (see Figure 19). The characteristics of this paint or chemical treatment must be the high degree of permanence, resistance to water, solar radiation and resistance to abrasion. An additional feature of such treatment should be easy detection by the device's camera 102 in all light conditions. For this purpose, the varnish can be, for example, fluorescent or the chemical treatment can produce a localized hair loss (for example, treatment with liquid nitrogen).

The second method is to apply a suitable adhesive that has a high contrast to the color of the surface of the subject observed in the anatomical region of the measurement. The sticker must show the pattern necessary to carry out the measurement. For example, the adhesive can be rectangular and can be applied in said anatomical region transversely to the spine, as shown in Figure 20. The same effect can be obtained with a suitable elastic band that reproduces the pattern in the anatomical region of interest. .

The third method is to use a laser generator 103 in position to project the reference pattern onto the anatomical region of measurement. For example, the laser can project a line transversely to the spine in that anatomical region.

A second embodiment consists in the implementation of a needle profilometer or an electronic type gauge comb. Such a device is characterized by the presence of a suitable number of needles that are parallel to each other and movable in one direction. Said needles are connected to electronic transducers that produce an electrical signal proportional to the position of each needle. Said transducers are then connected to a control unit 101, which can extract the profile 109 of the specific anatomical region observed, based on the electrical signal produced by each transducer. In this case, the technician will physically support this profilometer in said anatomical region, transversely to the spine. The profile 109 thus obtained is transmitted from the control unit 101 and processed by the processing unit E with the method described below to determine the degree of fattening index, the score of the body condition, the weight, etc. In this case, the mathematical transform used for this determination depends at least on the species and / or race, and / or sex. and / or age of the animal and is obtained in comparison with a reference population weighted by means of appropriate scales.

A third embodiment is the implementation of a flexor-electrical profilometer applicable to the body of the observed subject. Said profilometer consists of an adhesive strip or an elastic band that integrates within itself suitable transducers necessary for the detection of the profile of said anatomical region. Such transducers can be, for example, resistive or piezoelectric. The instantly collected data allows the profile 109 to be derived. Said data, continuously recorded from said sensor, describes the evolution of the profile of said anatomical region over time. The technician can apply such profilometer tape as a permanent or temporary adhesive to the body of the observed subject. Similarly, such a tape can be applied with felt. Also, this device could be applied under the skin. Such a device can be equipped with an RTLS (real time location system). In this way, the central processing process can know at any time the identity, position and body condition of each monitored subject. The knowledge of the instantaneous position allows to draw conclusions about the behavior of the subjects. In particular, on the state of heat, based on certain indicators such as increased movement and the reflex of immobility. As described below, the combination of FI, or BCS, with the heat status, allows the fertility index of the test subjects to be determined. Said device can also integrate a proximity or pressure sensor to detect the heat state by the so-called mounting reflex. In fact, when, for example, a cow is in heat, she induces the covering reflex in her companions, which corresponds to a female's simulation of a male attitude during breeding. This causes flattening of the caudal region of the subject in heat, which can be detected by suitable sensors. This information is added to that detectable using RTLS, to increase accuracy.

Such a device, by almost continuously monitoring the subject under examination, can detect other notable conditions, such as contractions associated with labor. In the zootechnical field, in particular, the detection of the moment of delivery of a newborn turns out to be of particular importance. Although BCS variations are relatively slow, labor contractions produce sudden changes in profile 109, in accordance with a recognizable pattern.

The profile 109 is then combined with the information from the sensors that may be present, transmitted by a control unit 101, processed by a processing unit E and processed according to the method described below to determine the synthetic fattening index, body condition score, weight, etc.

In Figures 7, 8 and 9, profile 109 is shown as produced by one of the described methods. In these representations, the case in which the observed subject is a bovine animal is considered, but the profile 109 appears to be similar in the case of another breed as well.

With reference to Figure 2, in Figure 2a, the lumbar region L and the sacral S in the case of cattle, in Figure 2b, the lumbar region L and pectoral P in the case of goats, in Figure 2c, the dorsal region D in the equine case, in Figures 2d and 2e, the lumbar region L is indicated in the case of felines and canines, in Figure 2f the abdominal regions A, femoral F, gluteal G, lumbar L, femoral F and pectoral P in the case of humans.

In the middle part M of said anatomical regions, a curve is produced that describes a profile according to one of the methods described.

Also defined is a first side of the observed subject 107, conventionally called the right side RS, and a second side opposite the first, conventionally called the left side LS.

In Figures 7 and 8, by way of example, a typical profile 109 of the lumbar region of a bovine is illustrated, with a left development 109L on the left side LS with respect to the direction of the spine S, and a development correct 109R on the right side LR with respect to said spine S.

The inventor has carried out an exhaustive investigation that led him to determine that from the shape of said profile 109 it is possible to obtain a synthetic fattening index FI and, consequently, a body condition score or BCS that represents, with good approximation, the body condition of the observed subject, as shown in a section below.

The analysis method consists of the following stages: (1) process profile 109 so that it is made up of a sufficient number of points, these points being distributed evenly and homogeneously and providing a certain degree of symmetry with respect to the spine ; (2) extract two representative synthetic numerical indices from the left side LS and the right side RS of that profile; (3) obtain a synthetic numerical index, here defined fattening index or FI, as a function of the index relative to the right side and one relevant to the left side of the profile observed in the anatomical region (specific index); (4) where profile 109 has been detected several times in the same anatomical region, calculating its average value; (5) where more anatomical regions have been examined, defining a global synthetic index resulting from the average of the specific indices of each anatomical region; (5) obtain the body condition score or BCS as a function of the fattening index FI, by an appropriate mathematical correlation formula, for example, of the linear type.

After determination of FI and BCS, using additional characteristic data of the observed subject, such as species, race, age and sex, the reporting method provides a good approximation of their body weight.

On the other hand, the present method makes it possible to derive an additional synthetic index, which represents the fertility status, the combination of the FI (or relative BCS) with the observed subject's heat status. This combination is implemented using a predefined mathematical transformation.

Now we describe, by way of example, but not by way of limitation, a possible implementation of steps (2) and (3) aimed at obtaining a synthetic index representative of the shape of the profile 109 of a specific anatomical region of the subject under examination, characterized by being dimensionless and as independent as possible of the position, the skill of the operator, of the skeletal characteristics of the observed subject.

Looking at Figure 8, and, in particular, Figures 8c and 8b, once P ^{m is} called the point of relative maximum, let us consider a first straight line a and a second straight line p that pass through P ^m and are tangent to the curve 109 .

Let P1 be the point of tangency between the second straight line p and the curve 109, P 1 the point of tangency between the first straight line a and the curve 109, Pb the point of intersection between the straight line aB passing through P1 and P 1 and the straight line S perpendicular to it and passing through P ^m (corresponding to the vertebral column of the observed subject), h the segment pmpb, ¿> 1 the segment p - \ pb, tí 1 the segment pipb.

Let us consider a third straight line y, parallel to the segment pip'i that crosses the straight line S at an intermediate position between P ^m and P ^b .

Let P2 and P 2 be the points of intersection between said third straight line y and curve 109, h 'and I segment pmph , tíi the segment ^ 2 Ph, ¿>' 2 the segment ^p 2 ^ph .

Taking into account Figure 8d, let a¿ be the angle between p mp2 and P 2P 2, in the angle between p2pi and ^ 1 P 1, a 2 the angle between p mp 2 and P 2P2, a ' 1 the angle included between segments P2P 1 and P j \ p a.

Let the angles j3i, £ 2, / 3'i and jS'2 be the complementary angles of respectively en, 02, a '1 and cr'2 (that is, so ai Pi = 7

than z).

The mathematical relationship proposed in this patent, that corresponding to the synthetic fattening index FI, for the evaluation of body condition is a function of these angles:

(1) R = f ( al, a 2, a \, a '2)

By specifying a left side LS and a right side RS with respect to the spine S, it is possible to calculate R only for the left side ( R ^l ) and R only for the right side ( R ^r ), obtaining R as an average of R ^l and R ^r , for example, as the arithmetic average:

(2) RL = f {al, a 2), R ^r = f {a \, a \)

Alternatively, it is possible to average the angles on the left and right side and then derive R based on these average angles:

(1b) R = f ( al, a 2)

where “1 and a 2 are the averages of the respective angles left LS and right RS of profile 109 with respect to column S, for example, calculated as arithmetic means:

The index R does not mathematically measure a convexity in any way, contrary to what was assumed in the two priority documents of the present application.

A preferred form of implementation of (1), (1a), (1b) and (2) is a function of the ratio of said angles and average angles:

where 0 is a generic angular displacement, such that 0 e [-n, n \.

A preferred form of implementation of (1c) and (2a) is as a function of the ratio of said average angles, according to the following formula:

ra 2 <p A ^ a 2 + a \ +2 <p ^

(1d) R = f = /

V «1 <p and ax + a \ +2 ( p

for example, implementable as:

es |a /-¿sima potencia de la relación de los ángulos promedio, que están desfasados por 0. El caso especial de (1d) es para n = 1:in which the coefficients k are constant, n is a natural number such that n> 1,

is | a / -th power of the ratio of the average angles, which are out of phase by 0. The special case of (1d) is for n = 1:

71

<P = T>

The particular case of (1 d ') is that in which z ko = 0, k \ = 1. In this case, R is a function of the relationship of complementary angles to a1 and a2 (angles £ 1 and £ 2 of Figure 8d):

Similarly, (2a) can be implemented as follows:

An additional form of implementation of (1) is based on the tangent relationship of these angles:

or, individually considering the two sides LS and RS:

An additional form of implementation of (1) is based on the ratio of the mean of the tangents of these angles:

f p

(1 e ”) R = f _{l 2}

v / i J

where these averages can be calculated, for example, as arithmetic averages:

tan (a ¹ + ( p) + tan (a'1 + ^?) tan (a ² + ^) + tan (<2'2 + ^)

K = _{e t2 =}

These formulas represent the averages of the tangents for the right side RS and the left side LS of profile 109, with respect to the spine S.

The preferred implementation form of (1 e) is:

í r x

(1 e ’”) * = í>, -v ‘i;

es la /'-ésima potencia de la relación de dichos valores promedio de las tangentes.in which the coefficients k, are constant, n is a natural number such that n> 1,

is the / '- th power of the ratio of said average values of the tangents.

Considering simplicity, as an example, the case of n = 1 , ko = 0, ki = 1, $ = 0, R can be calculated from (1e "') as:

tan (a2) + tan (a '2)

(1f) R =

tan (a1) + tan (a '1)

Similarly, the components can be obtained only for the right side RS and the left side LS:

from which:

The R index represents a new synthetic index for the evaluation of body condition, which we define here as the fattening index or FI.

A particular case is that of the muscles and the symmetry of the skeleton of the observed subject 107 with respect to the spinal column. In this case we have to:

(ig) R - R ^l - R ^r .

A special case is the situation where the profile 109 is not fully provided. This can occur, for example, in the case where the image taken by the camera 102 is partially covered or in the case that the profile of a part of the anatomical region under examination is detected. This can occur in the case of production animals, for example in a slaughterhouse after the animal has been slaughtered (post mortem). In this case, at the end of the slaughter line, immediately before being stored cold for the process of hanging to maturing, the animal, divided into two parts, is classified according to a standardized procedure. In Europe, for example, the SEUROP classification system is used, according to which cattle are classified according to category, muscular conformation and presence of fat. The shape is indicated by the letters S, E, U, R, O, P, which refer to muscle development; S exceptional with very convex profiles and high quantitative and qualitative slaughter yields; Low P, with straight profiles and low quantitative and qualitative yields.

In this context, the method described in the present document can be applied advantageously, in the particular case in which only half of the curve represented in Figure 8 is considered. Such condition is covered by the particular case (1g) in the that the two half curves are equal and symmetrical with respect to the line of the spine.

Substantially, in this case, it is a matter of acquiring only one lateral development of the profile 109 and completing this curve by calculating the development on the other side as a specular development with respect to the direction of the spinal column. The rest of the process is identical, except that the formulas are simplified thanks to symmetry.

It is possible to apply the method for calculating the R index several times in the same anatomical region and / or a plurality of anatomical regions of the same animal. In this case, a total index will be calculated, for example, as the average of the R values of each measurement, for example, by means of the arithmetic average:

where n is the number of measurements in the same animal, and Ri is the value of the fattening index for the / -th measurement. The fattening index, calculated by formulas (1d), (1e), (1f), (2b), (2c), represents an excellent indicator of fattening status according to what has already been discussed, regardless of the species, race, sex, age and absolute size of the observed subject.

However, the resulting numerical values are not within the same scale normally used in common practice by technical evaluators.

As illustrated in Figure 3 and as described above, the index called Body Condition Score, normally used internationally, varies on a scale of 1 to 5 (in some countries different scales are used, such as 0 to 5 in France or 1 to 9, in any case, related to each other by linear transformations).

To obtain a similar score from R , it is necessary to apply a transformation function:

(6) BCS = y / ( R, S, B, M, E)

where R is the rate of fattening, S is the species, B is the breed, M is the sex and E is the age of the observed subject. By setting S, B and M, and considering a specific age group, the function y ( R, S, B, M, E) can be calculated as follows (also for other scores such as the main body mass index) :

(7) BCS = y / ( R, S0, B0, M0, E0) = f ^ kiRi

i = 0

with n> 1 the order of the function V. The parameters k, are coefficients that depend on the species, race, sex, age group and can be determined empirically based on a group of reference subjects whose BCS has been evaluated by technical experts.

The method described is particularly effective in determining BCS for Holstein milk. The tests carried out show that formula (7) should be applied with a high degree of approximation with the same k \ parameters to Holstein cattle, regardless of age, stage of lactation and number of parts (primiparous or multiparous heifer).

In the case of men, the most widely used synthetic index is the body mass index or BMI, defined by the following formula:

where m is the weight in kg of the observed subject and h2 is the square of his height.

A modified version of BMI is defined as main BMI, corresponding to the relationship between the BMI of the observed subject and the upper limit of BMI of the reference population.

To the extent that the main BMI is a ratio of two different BMI values, the main BMI is a dimensionless number. Subjects with a main BMI of less than 0.74 are underweight; those between 0.74 and 1.00 have an optimal weight; and those over 1.00 are overweight. The main BMI is useful from a clinical point of view because it expresses in a synthetic way, for the observed subject, the percentage of deviation from the upper limit. For example, a person with BMI 34 has a main BMI = 1.36 (relative to an upper limit of 25), so he / she is 36% over his / her maximum weight.

For Southeast Asian and Chinese populations, the main BMI should be used by calculating an upper limit of 23, rather than 25 (typical for western populations).

The main BMI ( BMIp) is correlated with the R index according to a function of the type:

BMIfl = í ( R, C, ME)

in which C is the ethnic group, M the sex and E the age of the observed subject.

When fixing C, M and E, one has to:

where z, are experimentally determined coefficients, R is the / -th power of the index R, n is the order of the expression.

In addition to BCS and BMI, there are several other indices, such as the surface-based body shape index (SBSI), in any case related by a mathematical transformation to the fattening index R.

An important characteristic of said R index is the high degree of independence of the height h of the profile 109.

This implies a substantial independence of R with respect to changes in the position of the recording tool 102 or skeletal variations between individuals of the same body condition.

For example, a variation in the relative tilt of the camera 102 with respect to the observed subject 107, the profile 109 being the same in the real domain, produces a curve, in the image domain, that is more or less flattened. To illustrate this feature, let's consider Figure 8e. Let's consider the condition in which the technical expert detects two measurements, for example, taking two photos, slightly changing the position of the camera between one photo and the other. This produces a change in perspective and therefore a change in the shape of the profile 109 in the image domain. In Figure 8e, the two curves are schematically represented as obtained as a result of the variation in the inclination of the device.

In this example, it is observed that the height h of the curve changes by 25%. It can be easily observed that the proportion of the tangents does not vary and the proportion of the angles suffers a weak variation. On the contrary, measurements such as the area of the curve undergo a very important variation.

Here are some experimental data that illustrate and confirm what was said, referring to the curves shown in Figure 8e.

Consider a profile 109 viewed from two different angles by means of a scan triangulation system. The same condition is observable, for example, in two bovines with the same body condition and observed from the same instrument with the same inclination, characterized by a different skeletal structure, in particular, one of the two subjects is characterized by a very prominent spine . Under such possible conditions, the profile 109 in the image domain will undergo the deformation shown in Figure 8e. For example,

₁ P _{H 1} P _B = - PP ₁

consider a straight line and such that ^

For the first image one has:

7 * 2 = 193, b - 617, A "62210

a, = 16.3 °, a 2 = 19.8 °, ^ = 1.22,

l «i

For the second image one has:

Ti, = 241, ¿= 617, A = 77763

«, = 20, 1,«, = 24, 3, 1.21,

# 0 ^{= 1,23}

# 0 ^{= 1.23}

L "tan (" j)

As can be seen, a 25% variation in the height of the curve produces a 20% variation in the area under the curve, while the proportion of the angles in the two cases experiences a change of less than 1% and the proportion of the tangents does not change. Since the proposed method determines the synthetic fattening index R and, consequently, the BCS, as a function of the relationship of these angles, then it can be said that the FI and the BCS are sufficiently insensitive to changes in the position of the recording tool 102 with respect to its ideal location.

The fact that a deformation similar to that shown in Figure 8e may also be due to a more or less prominent position of the spine to be considered. In fact, the two curves shown in Figure 8e could correspond to two different animals, characterized by a different skeletal structure, but with the same body condition score (BCS). It is correct that the shape of the spine has little effect on the fat index and, consequently, the BCS, because the shape of the spine does not provide information on the fat stores accumulated by the observed subject.

This peculiarity of the proposed method shows an important difference with many of the methods of the prior art that examine the absolute dimensions of the observed subject (and its processing, such as the calculation of the area or volume under the curve), for example, obtained by scanning three-dimensional.

By virtue of this characteristic and the fact that the proposed method is independent of the real size of the flat profile 109, this method is applicable in a much wider range of devices than methods based on the use of three-dimensional cameras (for example, camera time of flight, ^t OR ^f ), such as in smartphones and, in general, in devices with a single low resolution camera.

Another optional feature of the method that is the object of the invention consists in the way of determining the points P1 and P 1, as points of tangency to the profile 109 of the observed subject 107.

It is considered, for example, to extract from the recorded image, by means of a digital image processing method, the pixels belonging to curve 109.

It is considered to have recognized N pixels, the / -th pixel of the curve 109 will be indicated with P, and the maximum of the curve with P ^m. With reference to Figure 9, let's consider the straight line through P ^m and Pi that has the equation:

(9) y = rtij.xc¡

in which:

With reference to the diagram in Figure 9, the algorithm for determining the point of tangency of the curve is based on the iterative comparison between the value assumed by the straight line (9) at the abscissa point x + 1 and the ordinate y + 1 from point P / + 1.

The point of tangency P ^t is identified when the following condition is verified:

The meaning of this condition is easily deduced from Figure 9.

The identification of the two points of tangency of the curve, which is indicated in Figure 7 with P / and P '/ allows to effectively apply the formula for the calculation of the synthetic fattening index R and consequently (6) for the calculation BCS also in the case where the observed subject is characterized by an asymmetric conformation (eg cattle). In the case in which a bovine animal is observed, the internal distribution of the organs determines a weak asymmetry between the right and the left side. In addition, it is common for the animal to stand with one of the hind legs more advanced than the other. This implies that the profile 109R is inclined and deformed with respect to the profile 109L.

The method just described for the determination of the points of tangency Pi and P'i overcomes this trouble.

This method is also advantageous to reduce the influence on the measurement of the inclination of the measuring device with respect to the spine. The user interface can be equipped with a level that indicates in real time the correct positioning of the instrument, in such a way as to assist the technician 108, at the time of measurement, to position the instrument properly.

With the algorithm of individuation of the points of tangency that we have just described, the set of effectively significant points of the curve is reduced, as the tails of profile 109 are eliminated (the intersection curve between a hypothetical plane and a specific anatomy observed region of subject 107).

Since FI and BCS represent synthetic indices of fat reserves of the observed subject, it is possible to use the BCS value obtained from formula (6) or the FI value obtained from formula (1d), (1e) and ( 1f) as a regressor, together with the race, age and sex of the observed subject, to obtain a good approximation of body weight.

This can be done by means of a polynomial regression based on a reference group of subjects of known species, race, sex, age and weight.

Therefore, once species, race, and sex are fixed, weight turns out to be a function of age E and BCS B:

(11) p = i ( e, b)

An example of such a function is represented by a polynomial regression that has the following form:

in which the first formula is the weight Pm of a male subject, age E and BCS = B.

The second formula is the weight Pf of a female subject, age E and BCS = B.

Obviously, the formulas (11) are specific to the species, race and age group.

In the case of production animals, cross breeds should be treated as a breed on its own.

The method for the determination of the m¡ and n parameters of the regression is known in the literature and is based on the use of the values of weight, BCS, age, sex, race and species of a group of reference subjects.

In the case of production animals, such as the milking of beef, the proposed method for the determination of FI, BCS and body weight, can be advantageously combined with the determination of heat to determine a new index of fertility status defined here fertility index F.

In intensive productions, in fact, fertilization occurs in almost all cases artificially (artificial insemination or FA). Given that, as is known, the milk production by a bovine is due to calving and the milk production curve peaks in the first months after calving and then decreases, the calving period should be minimized to maximize productive performance.

However, the cow is fertile for a few hours, so it is essential to determine the heat time to proceed with assisted reproduction at the time of maximum fertilization possibilities.

However, the chances of a successful fertilization depend not only on the heat status of the subject, but also on his physical condition. In fact, it is known that a subject in poor physical condition is unlikely to be fertilized. There are numerous studies in the literature that demonstrate the correlation between BCS variations and fertility, for example, in dairy cows. In summary, the existence of a body defense mechanism that prevents the conception of a new living being is known in the event that the person has an inadequate physical condition. This is probably due to the fact that in nature an inadequate physical condition, such as extreme thinness (BCS between 1 and 2 on a scale of 1-5), is associated with the scarcity of food resources in the environment, and then at an extremely low probability for the mother to successfully conclude the pregnancy and for the unborn to survive in the environment.

In intensive milk production, it is not uncommon to find very lean or very fat beef, or at least below or above optimal body condition. This is due to many factors that distinguish good breeding from poor breeding, but in any case due to the fact that meat for intensive milk production has been genetically selected to produce large daily amounts of milk in proportion to its body weight. . This implies an extreme precariousness of the energy balance of the cattle, which must be maintained in a manner appropriate to the stage of lactation in which it is, so that its energy balance is the most balanced possible. However, an unfavorable relationship between the cost of feed and the cost of the sale price of milk would make the cattle uneconomical. Therefore, the breeder is constantly looking for the right balance between the quality and quantity of feed, the health status of the cattle and the milk production, often having to accept a certain degree of inefficiency in their process. In this context, a significant economic weight is constituted by the cost of semen doses for artificial insemination.

In short, in the delicate economic balance of milk-producing farms, failing an insemination means losing the value of the seed (often very expensive) and delaying the launch of that subject's milk production for a month.

In light of what has been illustrated, in order to maximize the probability of fertilization, it is substantial to observe both the heat status and the body condition (BCS or FI) of dairy cattle.

There are a number of prior art techniques for the determination of heat in dairy cattle that can be advantageously combined with the present invention for the calculation of FI and BCS. These solutions exploit the behavioral traits or biological characteristics associated with heat status. Some are cited by way of example: pedometers and electronic collars, which detect increased motility of the subject; the so-called "tail paint" and its electronic versions, which detect the increasing reflection, induced by the state of heat of a cow in its companions; chemical analysis of milk, aimed at identifying specific chemicals associated with heat status.

In the present context, a fertility index F is defined for a subject in heat as the percentage change between the real BCSr value and the ideal BCS value of the subject in relation to its lactation stage, according to the following formula:

BCSr

⁽ 12 ⁾ F = E-

BCS,

in which E represents the state of heat (E = 0 absence of heat, E = 1 subject in heat), considering the BCS scale [1; 5], BCS, normally varies in the range [2,5; 3.5].

According to (12), the fertility index F can assume the following values and meanings:

1. F = 0, indicates the absence of heat, regardless of the condition of the body;

2. F = 1, indicates a heat condition with an optimal body condition ( BCSr = BCS,);

3. F > 1, indicates a state of heat in "overcondition";

4. 0 < F <1, indicates a state of heat in "subcondition".

So if F has values close to 1, then the probability of a successful insemination is maximum.

Figure 1 shows a graph of the prior art in which the time line is reported on the abscissa, in which zero corresponds to the date of the last calving, the dotted line 102 represents the trend of the ideal BCS (BCS,) and the solid line 101 represents the trend of milk production.

A second configuration of the apparatus D object of the invention can be used to make stationary plants of the automatic type. Apparatus D can advantageously be installed above those confined environments where animals must be closed for a short period of time for functional reasons, such as weighing, veterinary examination and / or drug administration, milking. In particular, the apparatus D can be used for the automatic measurement of the BCS inside the containment and / or weighing box, inside the milking robot, in the framework of the milking parlors.

As an example of said second configuration, consider Figure 11, in which the installation of apparatus D inside a weighing box B for livestock is shown schematically. The same methodology is applicable in any other type of condition in which the subject 107 is locked in a known position. This will allow the control unit 101 to be positioned in such a way that it optimally frames the region of anatomy (e.g. lumbar region) of the observed subject 107, in which the profile 109 is highlighted by means of one of the methods described. . The command to acquire the image, or sequence of images, can be given manually by a technician using a remote control, which would perform the function of button 106. Alternatively, if there is a front and / or rear door, switches can be used limits that allow the control unit to identify the moment when the animal is actually present inside the box. For this purpose, other types of presence sensors, such as infrared, microwave, ultrasonic sensors, RFID readers can also be advantageously used in the case where the animal is equipped with transponders for electronic identification. With the same objective, within the control unit, a motion detection application can be implemented that allows detecting the presence of an animal, automatically determining the optimal moment for image acquisition.

In the same way, the identification of the animal can be carried out manually by the examiner by means of a remote terminal that is connected by radio frequency to the control unit 101. In the alternative, to automate the process, the control unit 101 can be connected to an RFID reader indicated in the figure with the letter R. Another possible alternative applicable in the field of fur animals or animals provided with a mark on the back consists of the implementation of a software application for the automatic recognition of such spots and / or marks, recorded by the camera 102, in order to uniquely identify the subject 107. In this second configuration, the apparatus D can interact with other measuring instruments present therein, such as the weighing terminal T for the simultaneous registration of the weight of the animal 107, the milk meter in the case of milking robots, the heat detection system, other remote terminals for e l registration, by veterinarians and / or technicians, of the drugs administered and / or the prophylaxis performed and / or any other type of examination or useful note.

In the same control and processing units of the system proposed here, an algorithm for the recognition of the heat state of the observed subject can be advantageously integrated, by means of the glue painting method. As is known, such a method consists in painting the tail of a cow with a suitable fluorescent paint. At the time that individual is in heat, the covering reflex is induced in the partners, which causes an abrasion of the caudal region in the observed subject. Such abrasion determines the partial or total removal of the previously applied paint. This change is detectable by means of the same video recording apparatus 102 used for profile detection 109.

With reference to Figure 12, the second configuration of apparatus D can be installed in the rotary milking parlor. This implies, as already illustrated in Figure 11, that said control unit 101 and said camera 102 (for example, integrated in the control unit 101) are placed on a support positioned upwards with respect to the observed subject 107, in where at least one profile 109 has been highlighted, by means of one of the methods described. In this type of milking parlor, the animals run in a kind of carousel, so that, by fixing the device D hanging from the ceiling, as shown in Figure 12, all the animals will pass under it, in a position known, before exiting the carousel. An automatic trigger (for example, photoelectric switch, mechanical switch, proximity sensor) will perform the function of the button 106 illustrated in Figures 6a and 6b, communicating to the control unit 101 the optimal moment in which the acquisition of the image via camera 102. Also in this case, all solutions for animal identification and interface solutions with other systems and the technician are applicable, already illustrated in the case of installation inside the weighing box (first configuration).

A third configuration of the apparatus D object of the invention can be used to make mobile systems of the automatic type. In fact, the apparatus D can be mounted on an air guide that operates its automatic handling within a milking parlor. This configuration is applicable to any type of room (eg herringbone, parallel).

As an example of a third configuration of this type of apparatus D, consider Figure 13, in which the apparatus D object of the invention is installed in a milking parlor of the "tenon" type. In this room, during the milking stage, the animals are trapped in known positions. In this context, the control unit 101 can advantageously be suspended in an air track 110, together with said chamber 102. In this configuration, the apparatus D is moved along the air guide 110 by the motor 111 by means of suitable motion transmission elements (for example, belt, chain, screw) and receives the command to release the photograph by means of a suitable self-timer (for example, photoelectric sensor, mechanical switch, proximity sensor) that performs the function of the button 106 illustrated in Figures 6a and 6b, communicating to the control unit 101 the optimum time in which the image will be captured during movement along the guide. Triggers must be placed in correspondence with each animal. The shutter speed of the camera 102 and the lighting system in the room must be suitable for the speed at which the device D is intended to move, so that the images are sharp and well exposed. The same solution is applicable to any other type of milking parlor (eg "parallel" type). Also in this third configuration, all the animal identification solutions and the solution for the interface with other systems and with the technician, which have already been described for the previous configurations, can be advantageously applied.

With reference to Figure 17, a fourth possible configuration consists in making a passage that the animals can traverse. By suitable proximity sensors of the type described in the above configurations and / or by appropriate electronic systems for identifying animals of the type described in the previous configurations, the actual position of the animal in transit through space can be determined. In this way, it is possible to determine the optimal moment in which the image is taken by means of the photographic apparatus, to record the anatomical region under evaluation, which has been highlighted in profile 109, in a plane transverse to the spinal column. , using one of the methods described, as illustrated in Figure 17.

Even in this fourth configuration, all the animal identification solutions and solutions for interface with other systems and with the technician, which have already been described for the previous configurations, can be advantageously applied.

With reference to Figure 21, a fifth possible configuration consists of placing appropriate high-resolution cameras 102 on top of the housing boxes of the animals 107, in order to be able to record, with a predetermined rate of time, the animals, in which the profile 109 has been highlighted by one of the methods described. The method and apparatus D described above can also be used to assess the BCS of a deceased animal (for example, post-mortem along the slaughter line), to classify its carcass, and in any case of the incomplete animal. .

With reference to Figures 14, 15 and 16, the acquisition, control, preprocessing and processing functions are illustrated in both the case of manual configuration and in the case of automatic configuration.

In particular, reference is made to Figure 14, relating to the portable tool controlled manually by a technician, according to the first configuration of apparatus D. Before carrying out the BCS measurement, the technician 108 performs a step 1 which consists of the identification of the subject 107 to be examined, manually registering a new individual data record in the data processing unit E or manually selecting the subject within a database comprised in said data processing unit E. This process it can be accelerated by the implementation of a voice interface in the control unit 101 based on prior art solutions such as ASR ( Automatic Speech Recognition) and TTS ( Text to Speech). In this way, the technician can identify the animal by speaking the last digits of the ear identification mark or the digits of the company number associated with the animal, or even by saying the name of the animal. Obviously, this data must have been preloaded in the database integrated in the control unit 101, which, once the voice control is decoded, can confirm to the technician by means of the TTS (text to speech).

This identification process can be automated by means of electronic identification devices such as subcutaneous transponders or electronic ear tags or electronic endoruminal boluses or electronic pedometers or electronic necklaces and the like. In fact, in the case in which the examined animal 107 is equipped with one of these electronic radio frequency identification tags, the technician 108 can identify it by means of a portable reader of the RFID type ( radio frequency identification), for example, connected via suitable wiring, or via Bluetooth or Wi-Fi with the control unit 101 or integrated into said control unit 101.

In this way, the F1 identification stage would be easy and fast.

Technician 108 at this point presses button 106. Process F2, as soon as button pressure is detected, executes step F3 of verifying the presence of a laser generator. When said laser generator is present in the system, step F4 of turning on said laser generator is carried out. The technician, with the help of the projection of the visible laser plane on the back of the animal, will carry out step ^f 5 of optimal positioning of the apparatus D with respect to the observed subject 107, to record the morphological character used for the determination of FI and BCS (for example, lumbar profile). At a time when the technician has identified the optimal position, he presses the button 106 again. This action is detected by the process F6 that will carry out the step F7 of image acquisition and turning off the laser.

In the case where there is no laser generator present in the system, for example, because the profile 109 has been highlighted by another technique among those described, the technician 108 will simply press the button 106 once. This action causes the execution of the acquisition stage F7.

If the technician wishes to acquire more photos of the same subject, then the process starts again from the F2 stage, otherwise, it provides the identification of a new animal that returns to the F1 stage.

In the case where the instrument is of the portable type according to the first configuration, the technician 108 stands before or backwards with respect to the subject 107 and positions the apparatus D to record the profile 109, highlighted by one of the methods described. Placing the technician 108 in front of the observed subject 107 seems particularly advantageous, possibly while eating, because in this condition, the examiner 108 can perform the measurement safely, staying in the "clean area" of the barn, outside the box. containment of animals.

Apparatus D appears to be robust to the subjectivity of the technician in its positioning in terms of height and inclination with respect to the observed subject 107.

Reference is now made to Figure 15, relevant for the fixed tool in automatic configuration, according to the second and third configuration of apparatus D.

Stage F2 consists of the process of detecting a new entity 107, by means of at least one of the sensors described in the first and second configurations.

The second configuration establishes that the apparatus D is fixed and that the animal 107 moves until it reaches the measurement position, the third configuration establishes that the animals are fixed in known positions and the apparatus D moves in the optimal measurement positions, the fourth configuration states that the animals they pass freely through the space along one direction, while the fifth setting states that the animals will move freely in the system's control area.

In these five configurations, the detection of the presence of a new animal can be performed manually by the examiner by means of a remote control, which would perform the function of the button 106 or automatically by suitable hardware or software sensors. For example, where front and / or rear containment doors are present, limit switches may be used that allow the control unit 101 to determine when the animal is actually in the measuring position. For this purpose, other types of presence sensors can also be advantageously used, such as infrared, microwave, ultrasonic, mechanical sensors, RFID readers where the animal is equipped with transponders for electronic identification. With the same objective, a motion detection application can be implemented within the control unit, which allows detecting the presence, position, orientation and direction of the animal's movement, automatically determining the optimal moment for the acquisition of the picture.

Once the presence of a new subject is detected in the measurement position, the system goes to the stage F1 of identification of the subject. The identification process can be sequential and synchronous with the other analysis stages or completely asynchronous and separate. In both cases, the control unit 101 will need the results of the identification process.

This identification process can be performed according to various techniques of the prior art: manually by the technician via a remote terminal connected by cable or wireless to the control unit 101. Alternatively, to automate the process, the control unit 101 can be connected to a RFID reader, where the animal is equipped with an electronic identifier. Another possible alternative applicable in the case of animals with feet or equipped with a mark on the back, consists in the implementation of software for the automatic recognition of such spots and / or marks, in order to uniquely identify the animal. .

Once the subject is detected and identified, where a laser generator is present (step F3), the system provides to turn on said laser generator (step F4) and acquire at least one profile (step F7).

Once this sequence is completed, the system returns to the presence detection process in step F2. The processing process can take place even in the absence of animal identification, where the interest is to calculate an average Fi and / or an average BCS of a group of animals.

Figure 16 shows the preprocessing and data processing processes.

Preprocessing is preferably implemented in the control unit 101, which, once a new profile is available (step S1) provides encryption of all data (e.g. animal data, data collected by sensors, data collected by other connected measurement systems, data entered by a technician, taking pictures or sequence of photos), their encoding within a single compressed data packet according to prior art techniques (e.g. watermarking techniques) and their forwarding to the remote processing unit or local processing processing unit (step S2).

The data processing process is preferably implemented in a remote central unit (processor), with all the features of computing power, memory, redundancy, business continuity, disaster recovery, etc., which guarantee processing speed and reliability. data security.

This process is constantly waiting for new data to be processed (step E1). As soon as a control unit 101 receives a new packet, the central system (containing at least one processor) executes its processing (step E2) according to the following steps:

- extraction, decompression and decryption of the data contained within the received packet,

- data consistency check,

- application of the process described in Figure 10 or another similar process for the determination of the tangency points of the curve 109,

- application of at least one of the formulas (1d), (1e), (1f), (1g) for the determination of FI,

- application of formula (8) for the determination of the BCS for the specific breed,

- application of formula (11) for weight determination,

- application of formula (12) for the determination of fertility,

- storing the information in the appropriate tables of the central database.

After being processed, the data can be made available to the user (step E3) (for example, transmitted to the device D and / or transmitted to another database and / or published on a web page).

The region of the lower back L, abdominal A, sacrum S, femoral F, pectoral P, gluteal G and dorsal D, depending on the species, is particularly significant for the purposes of evaluation of the BCS, in its middle part M, given that it is in such regions where fats accumulate mainly in the case of greater availability and are mobilized faster in conditions of need. The best evaluation of FI by formulas (1d), (1e) and (1f) and the BCS by formula (8) is obtained by highlighting, using one of the methods described, the profile 109 in its central region.

In general, profile 109 tends to change shape, to change from said M mid-region.

In the case of the lumbar region in dairy cattle, it was observed that forward or backward movements from the optimal position, even within the lumbar region, produce small variations in FI and BCS, which have little influence on the BCS estimate for common use.

With reference to Figure 22, a further apparatus PG is proposed for the application of the method according to the present invention. This apparatus consists of an improved electronic needle profilometer comprising several needles 126 parallel to each other and movable in one direction, at least one digitizing system for digitizing the position of said needles 127, at least one data processing unit E, at the minus one peripheral user interface 125. Such apparatus PG includes physical contact between the instrument and the animal, as opposed to apparatus D which instead performs non-contact measurements.

When this improved needle profilometer PG rests on an anatomical region of the animal 107, it will describe the profile 109 with a resolution proportional to the number of needles used. The control unit 101 converts the dislocation of said needles into an electrical signal processable by a local or remote data processing unit E.

With reference to Figure 23, a further SG apparatus is proposed for determining the body condition score of an animal 107. Such apparatus comprises at least one flex-sensitive band 131 composed of a suitable number of electronic strain gauges 130, at least one system for digitizing the signal produced by said strain gauges, at least one data processing unit E, in which said flexural sensitive band 131 is applicable on the surface or under the skin of the observed subject.

Such an apparatus, by means of electronic strain gauges 130, can detect expansion 132 or compression 133 along the direction perpendicular to the spine of the animal 107, to describe the profile 109 with a resolution proportional to the number of gauges of tension integrated in said band 131.

These electronic strain gauges are connected, by cable or wirelessly, to a local or remote data processing unit (E), capable of extracting an actionable profile 109 according to the techniques already described.

With reference to Figure 23, a further apparatus S3 is proposed for the application of the method according to the present invention. This apparatus consists of a three-dimensional scanner, according to a known technique, for example, of the TOF type (time or flight), connected to a control unit. Such a set makes it possible to acquire the profile 109, which is processed by a processing unit to obtain the FI index, the BCS, the estimated body weight and the fertility index, as already described.

Experimental tests

Here follows a comparison table between BCS evaluated by an experienced veterinarian and that of the system in two separate test sessions on the same group of animals.

This test was performed "double blind" in Holstein subjects in two test sessions (A and B), recording the determination made by an experienced veterinarian and processed by the system in question according to formula (8). The first column shows the company identification number of the animals, the third and sixth column shows the BCS values estimated by the system in the two tests A and B, the fourth and seventh column list the opinions expressed by the expert vet. As shown, the system shows very high repeatability in determining BCS in the same subjects. Furthermore, in 85% of the cases, the difference between the judgment of the system and that of the evaluator is less than a quarter of a point.

Some new features over the prior art

The apparatus D and the method object of the present invention present some substantial peculiarities with respect to the known technique.

In particular, the method to determine the FI and BCS and its application tools allow the evaluation of the body condition of an animal to be carried out automatically, definitively overcoming the problem of subjectivity in the visual evaluation by an evaluator and in the Al at the same time, reducing the degree of complexity of the examination in such a way that the method is applicable to simple and portable instruments.

Furthermore, in the case of a portable application, the proposed system significantly reduces (5-10 seconds) the detection time and the evaluation of BCS with respect to any other portable or visual inspection method. In the case of a fixed system, equipped with an electronic device for the identification of the animals, the analysis time is reduced to the shutter time of a camera (shutter time of an order of magnitude equal to fractions of a second).

In the case of the portable application for the measurement of BCS in cattle, in contrast to the common practice of observing the animals from behind and then inside the animal containment box (dirty area), the technician can perform the measurements by positioning in front of the animal, outside the boxes.

It is particularly advantageous to use the tool while the animals eat with their necks caught in the containment fence. In this way, the technician, who remains in the feeding corridor, that is, in the clean area, can carry out the BCS detection of all "trapped" animals in a rapid sequence, with maximum safety and minimization. the time required for the measurement of the entire flock.

Furthermore, in the case of a portable application, the proposed system appears to be robust to possible positioning errors related to the observed subject and skeletal variations between individuals having the same body condition.

This makes the system substantially independent of the technical expert who uses it. Changes in the position of the measurement system relative to the observed subject, such as tilt and height, do not significantly influence the BCS value. Higher skill influences only acquisition speed.

In the case of the application combined with an electronic identification system for the identification of the observed subject, the acquisition speed increases even more.

In case of application to animals with fur coat or provided with a mark that makes them visually recognizable (for example, a code printed on the back), the proposed system can advantageously use image processing methods to identify the animal on the base of an image, simplifying and speeding up the measurement process even more.

The proposed method can be applied both in portable type tools and in stationary type solutions. In particular, it can advantageously be installed in a stationary manner with automatic operation in any milking parlor, milking robot, weighing or animal containment boxes, passageway and stall box. The proposed method can also be applied to air detection, for example installed on board a drone or helicopter.

In the area of herd monitoring, said solution can be advantageously combined with other visual and / or morphometric and / or biometric solutions for animal identification.

An important novelty of the invention consists in the independence of the method and its body condition index FI with respect to the species, race, sex, age and absolute size of the observed subject.

Another novelty of the invention lies in its ease of implementation, robustness to environmental changes, substantial independence from the user's capacity, in its applicability in portable solutions. These characteristics make the invention particularly suitable for the application context of a barn. In the present invention, in addition, only one morphological trait (profile) is evaluated in a specific way, the veterinarian considers 5 or more of them. By precise mathematical correlation, the invention can reduce the number of evaluations.

The proposed method also has the advantage over the known prior art of being able to be implemented even in simple devices (eg smart phones) without the need for additional equipment. This is a direct consequence of the fact that the method of the invention analyzes profile 109 regardless of its absolute physical size.

In the foregoing, preferred embodiments have been described and variants of the present invention have been suggested, but it should be understood that modifications and changes may be made by those skilled in the art, without departing from the related scope of protection, as defined by the appended claims.

Claims (21)

1. Method to determine a numerical index indicative of the energy reserves in the form of fat stored by a dead or live animal (107) of any species and race, including humans, for example, the body condition score or the mass index corporal, in which the following stages are carried out: A. digital detection, by means of optical detection of reference elements, applied or projected on the body of the observed subject, or by another type of detection system, with or without contact, of at least one profile (109) of a anatomical region of morphological interest, said at least one profile being defined as the shape of the curve that describes at least part of the outer perimeter of a section of said anatomical region, said curve extending over an imaginary plane said anatomical region; B. sending said at least one profile (109) from step A to at least one data processing unit (E); C. calculate a numerical index R indicative of the energy reserves in the form of fat accumulated by the animal, in particular, in said anatomical region, by means of at least one data processing unit (E) on the basis of said at least one profile (109) of stage A; Y D. correlating, in said at least one data processing unit (E), by means of a predefined mathematical transformation, said numerical index R with one or more state characteristics of said animal; wherein in the body of the animal a first side (LS or RS) of said anatomical region is present with respect to the spine of the animal (S) or a first side and a second side (LS, RS) of said anatomical region with respect to the vertebral column (S) of the animal, and in which said profile includes a point of relative maximum P ^m in the vertebral column of the animal and a first development of the profile (109L or 109R) on said first side or a first and a second development of the profile (109L and 109R) respectively on said first and second side (LS, RS), the method being characterized in that stage C includes the following sub-stages: C1. individualize the coordinates of the relative maximum point P ^m of said profile; C2. determine a first straight line (P) tangent to said profile (109), starting said first straight line from the relative maximum point P ^m and touching said profile at a first point of tangency P ¹ of said first side, or in addition to the first straight line of tangency that also determines a second straight line of tangency (a) that extends from the point of relative maximum P ^m and touches said profile at a second point of tangency P1 on said second side; C3. in the case in which in stage 2 only said first point of tangency P ¹ was calculated, taking as the second development (109L, 109R) of said profile the specular projection of said first development with respect to the direction of the spine, and assuming as the second point of tangency P 1 the specular point to said first point of tangency P ¹ with respect to the direction of the spinal column; C4. calculating a first dotted line point P ² and a second dotted line point P 2 as the intersection between said profile and a straight line (y) parallel to a base segment running from P ¹ to P ¹ ; C5. calculate said numerical index R as:

where 02 is the angle between the segments ^pm p2 and P2P 2, en is the angle between the segments p2pi, and pip 1, cr'2 is the angle between the segments pmp 2 and P2 P2 I a ' 1 the angle between the segments p 2p i and P'iPi, and in which 02 = cr'2 and a1 = a'1 in case of the assumption of step C3. 2. Method according to claim 1, wherein in step C5 first a synthetic index R ^l relevant for said first development (109L) and a synthetic index R ^r relevant for said second development (109R) are calculated as

and then: R _ Rl + Rr two 3. The method according to claim 1 or 2, wherein: R = f ( al, a 2) or:

or:

or

or

or:

or:

or:

or

or

where the coefficients k, are constant, n is a natural number, and n> 1.0 is an angular displacement such that 0 e [-tt, tt \, ai is the average value of the angles ai and cr'i, a2 is the average value of angles 02 and cr'2,

i- th power of the ratio of the average angles with an angular displacement 0, 1 is the average value of the tangents of angles 02 and cr'2,

is the i-th power of the ratio of these mean values of the tangents. 4. Method according to claim 3, wherein: _R tan (< 2 2) + tan (a'2) tan («1) + tan (a'1) or: tan (a2) tan («'2) ^ _ R ^l + R ^r _ tan (a1) tan (a'1) _ tan (a1) tan (a'2) + tan (a'1) tan (a2) 2 2 2tan («1) tan (a'1) Method according to any one of claims 1 to 4, in which the parallel straight line (y) is positioned in such a way that the line perpendicular to said parallel straight line (y) and passing through P ^m a point Ph is crossed in said straight parallel line and in said base segment a point Pb such that the segment phpb is substantially equal to the segment PMPH. 6. Method according to any of claims 1 to 5, wherein in step D the numerical parameters of said mathematical transformation depend at least by species and / or race and / or ethnicity and / or age of the subject and are obtained compared to a reference population evaluated according to a traditional method or a different prior art measurement method. 7. Method according to claim 6, wherein in step D the following substep is performed: D1. correlate, by means of a first predefined mathematical transformation, for example a linear transformation, said numerical index R from stage C with a visual and tactile scale of scores, such as, for example, the linear score or the body condition score of known use, in particular known in the traditional assessment of the body condition of production animals, companion animals and humans, and which is obtained in comparison with a reference population evaluated by technical experts and / or by others means known in the art. Method according to any one of claims 1 to 7, wherein after step C the following additional step is carried out: E. correlate, using a second predefined mathematical transformation, said numerical index R of stage C, with the weight of the animal, said mathematical transformation depending at least on the species and / or race and / or gender and / or age of the animal and obtained by comparison with a reference population weighted by means of appropriate scales. 9. Method according to any one of claims 1 to 8, wherein after step C the following additional step is carried out: F. correlate, by means of an additional predefined mathematical transformation, said numerical index R of stage C with the degree of fertility of the subject under examination, resulting from the combination between the numerical index R and the state of heat, detected by means of testing tools. prior art. Method according to any one of the preceding claims, in which said profile is a profile of an anatomical region chosen from the group comprising the lumbar (L), abdominal (A), sacrum (S), femoral ( F), breast (P), gluteal (G), dorsal (D) or the skull of the animal (107), particularly in its middle area (M). Method according to any one of the preceding claims, in which said imaginary plane is a plane transverse to the spinal column of the animal. Method according to any one of the preceding claims, in which the detection system is a profilometer, such as triangulation scanners (for example, laser lines with optical registration), time-of-flight and phase difference scanners or comb gauges or tape measure sensors. Method according to one of the preceding claims, characterized in that the profile detected in step A is sent to a control unit (101), which carries out its compression and associates additional data on said animal (107) , and subsequently sends it to said at least one data processing unit (E), local or remote. Method according to claim 13, characterized in that said additional data is data detected by one or more sensors, in particular, chosen from the set comprising: accelerometer, magnetometer, gyroscope, thermometer, GPS, Wi-Fi locator , RFID reader (radio frequency identification), RTLS locator (real time location system), system for detecting the state of heat and personal data of the animal (107). 15. Method according to one of claims 5 to 14, characterized in that said score of body condition, main body mass index or other scoring scale for body condition, once the species and / or ethnic group and / or race and / or sex is fixed, it can be obtained from the numerical index R or of the synthetic fattening index, through a function of the type: Í k r ' i '= U in which n is an integer greater than 1, R ' is the i-th power of R and the parameters ki are specific constants of the population to which said animal (107) belongs, determined, for example, by species and race, and which are determined in comparison with a reference population evaluated visually or with other instruments of the prior art, according to the traditional method. 16. Apparatus (D) for determining a numerical index indicative of energy reserves in the form of fat accumulated by an animal (107), comprising at least one contact or non-contact detection system (102, 103, 124, 125, 126, 128, 129, 130) for the detection of the profile (109) of the animal (107), at least one control unit (101) and at least one data processing unit (E), local or remote, connected to said control unit (101), wherein said data processing unit (E), local or remote, includes a program configured so that, when executed, it performs steps C and D of the method according to any one of claims 1 to 15. 17. Apparatus (D) according to the preceding claim, characterized in that said contact or non-contact detection system for detecting the profile (109) of the animal (107) can alternatively be: a) a camera (102) adapted to acquire images of one or more animals (107) with the profiles (109) highlighted by projecting a coherent or non-coherent light pattern or by prior application of paint or adhesive or elastic bands suitable in the body of the animal, said camera (102) being connected to said control unit (101), which integrates functions of digitizing images and / or data compression and encryption and / or user interface, and / or transmission of data; b) an apparatus (PG) comprising a suitable number of needles (126) moving in one direction and at least one digitizing system (127) for digitizing the position of said needles, wherein said moving needles are configured to rest on the body of the animal (107), which describes a profile (109) with a resolution proportional to its number, and in which said digitization system (127) is configured to convert the dislocation of said needles into an electrical signal processable by said data processing unit (E); c) an apparatus (SG) comprising at least one flex-sensitive band (131), composed of a plurality of electronic strain gauges (130), and at least one signal digitization system to digitize the signal produced by said electronic strain gauges, wherein said flex-sensitive band (131) is applied to the surface or under the skin of the animal (107), and by means of electronic strain gauges (130) is configured to detect the expansion (132) or compression (133) along the direction perpendicular to the spine of the animal (107), to describe a profile (109) with a resolution proportional to the number of tension meters integrated in said band (131) , said electronic strain gauges being connected to said data processing unit (E). Apparatus (D) according to claim 16 or 17, further comprising at least one position sensor (P) configured to detect the positioning of said apparatus (D) with respect to the position of said animal (107). 19. The apparatus (D) according to any of claims 16 to 18, wherein said apparatus (D) is portable and includes: - an extension arm (105) adapted to be held at a first end and supporting said control system (101), such as, for example, a smartphone, in which said camera is integrated (102) at a second end ; - a laser arm (104) connectable at a first end to said extension arm (105) with which it forms, for example, an angle of 135 °, and which comprises said laser generator (103) at a second end; Y - an actuator (106), arranged at said first end of said extension arm (105), configured to control said laser generator (103). 20. The apparatus (D) according to any one of claims 16 to 19, characterized in that it alternatively comprises a sensor for the presence of the animal in a predetermined area, said sensor for the presence of the animal sending its detection to said control unit ( 101) for the start of step C of the method, or a reader of an identification tag placed on said animal, said identification tag reader being connected to said control unit (101). 21. Apparatus (D) according to any one of the preceding claims 16-20, characterized in that It comprises a system for detecting the heat status of the animal according to prior art techniques, the combination of the body condition score with the heat status providing a new indicator defined herein as the fertility index, determined according to the following formula:

in which E represents the heat state, in which E = 0 in the absence of heat and E = 1 in the presence of heat, BCSr the real value and BCSi the ideal value of the animal's BCS , in which the index of fertility F can take the following values and meanings: - F = 0, indicates the absence of heat, regardless of the condition of the body; - F = 1 indicates heat condition and optimal body condition ( BCSr = BCSi); - F > 1 indicates a heat state in "overcondition"; - 0 < F <1 indicates a state of heat in "subcondition".